magnus/agent-skills
1
1
Fork 0
Code Issues Pull requests Projects Releases 5 Packages Wiki Activity Actions
5 releases 5 tags
  • v0.2.2 14c3fa286e

    v0.2.2 — Add brand-designer skill Stable

    jasper released this 2026-05-24 19:13:08 -04:00 | 8 commits to main since this release

    What's New

    brand-designer skill (new)

    A comprehensive toolkit for creating brand identity documentation. Guides users through documenting strategy, visual identity (logo, color, typography, imagery), voice and tone, application guidelines, governance, and asset inventory. Produces structured markdown specs, compiled brand books, and brand-compliant images via reference-image-aware generation.

    Includes:

    • 7 markdown templates (brand-card, strategy, visual-id, voice, application, governance, asset-inventory)
    • brand-book CLI for scaffolding, compilation, validation (init, compile, validate, preview)
    • generate script for brand-compliant image prompt construction
    • 6 reference files covering canonical components, format analysis, artifact hierarchy
    • 12/12 passing test suite

    Documentation

    • AGENTS.md — Added trigger entry for brand-designer keywords
    • README.md — Added brand-designer entry in alphabetical order

    Files Changed

    19 files changed, 3,063 insertions, 1 deletion

    Downloads
  • v0.2.1 f902c663ef

    v0.2.1 — Nous Branding Skill Stable

    jasper released this 2026-05-24 13:37:42 -04:00 | 10 commits to main since this release

    v0.2.1 — nous-branding skill

    Adds the nous-branding skill: a comprehensive brand identity guide for generating images and content in the Nous Research visual style.

    What's inside

    Brand documentation — color palette (Electric Blue #3847FF + 5 more), typography (Inter/IBM Plex Sans, JetBrains Mono, heavy distressed display), Nous Girl mascot specs verified against the official brand booklet, texture system (risograph grain, photocopy noise, CRT scan lines), design principles, and a brand compliance checklist.

    7 reference images — 3 extracted from the official Nous brand booklet (badge portrait, character sketch sheet, philosophy page) plus 4 generated assets (palette card, style reference, brand collage, web mascot). These can be uploaded as img2img inputs.

    scripts/generate-with-ref.py — a script that reads your Hermes Agent config, detects your image generation provider, and hits the API directly with a reference image upload. For OpenAI, this uses /v1/images/edits with multipart form upload — the only way to feed reference images into gpt-image-2. This produces dramatically better brand consistency than text-only generation (verified 10/10 character faithfulness vs ~6/10 from text).

    How to use

    # Load the skill
skill_view(name='nous-branding')

# Generate with text only
image_generate --prompt "HERMES KANBAN poster ..."

# Generate with reference image upload (recommended)
python3 scripts/generate-with-ref.py \
  --prompt "Your prompt" \
  --reference assets/nous-girl-official-badge.png \
  --aspect landscape
    Downloads
  • v0.2.0 7c8b0ece9f

    v0.2.0 — Data Scientist + EPUB Skills Stable

    jasper released this 2026-05-23 18:10:52 -04:00 | 13 commits to main since this release

    v0.2.0 — Two New Skills, 50 Files, 12,792 Lines

    This release adds two major new class-level skills — data-scientist and epub —
    plus significant expansions to both. 50 files changed, +12,792 lines.

    New Skill: data-scientist (data-scientist/)

    PhD-level data science expertise for AI agents. Eight competency domains, from
    mathematical foundations through experimental design, causal inference, Bayesian
    analysis, ML, MLOps, and research leadership.

    • SKILL.md — 255 lines: decision framework, question classifier, response rigor
      matrix, statistical philosophy (assumptions-first, effect sizes over p-values)
    • 6 Python scripts: power-analysis, assumption-diagnostics, effect-size-calculator,
      experimental-design, model-comparison, detect-compute (hardware probing)
    • 16 references covering: experimental design, causal inference, Bayesian
      workflow, regression modeling, statistical methodology, PCA workflow, and
      newly added: Docker experiment isolation (301 lines), subagent experiment
      supervision (389 lines), experimental campaign protocol (577 lines, 8-phase),
      PyTorch integration (616 lines), scikit-learn integration (577 lines),
      data science coding workflow (489 lines)
    • 4 test suites — campaign protocol, compute detection, references completeness,
      supervision protocol

    New Skill: epub (epub/)

    Complete EPUB creation, editing, validation, and knowledge extraction skill.
    Built from EPUB 3.3 spec research and real-world testing on a 2.1MB commercial
    Apress EPUB with Apple Books compatibility verification on macOS 26.

    • 11 CLI scripts following cli-builder patterns (--json, --dry-run, lazy deps):
      scaffold, edit (8 subcommands), info, text extraction, knowledge extraction
      (heuristic + LLM auto-detect via env vars), validate, images, batch, convert,
      repair, cover
    • 9 references including new apple-books-compatibility.md — verified rendering
      rules: cover XHTML wrapper requirement, OEBPS/ directory structure, deprecated
      CSS avoidance, spine ordering patterns (3 variants), XHTML namespace handling
    • LLM env var convention — scripts auto-detect EPUB_LLM_URL + EPUB_LLM_KEY
      and enable LLM features automatically; silent fallback to heuristic mode
    • 46/46 tests passing in test_epub_skill.sh

    Data Scientist Expansions

    • Subagent supervision — protocol for spawning worker agents to run experiments
      in parallel with automated health monitoring and result collection
    • Docker experiment isolation — reproducible, containerized data science
      environments with pinned dependency hashing
    • Experimental campaign protocol — 8-phase research workflow from problem
      formulation through publication, with phase-specific templates and completion
      criteria
    • Code integration references — PyTorch, scikit-learn, and general DS coding
      workflow with agent-specific patterns for library usage
    • detect-compute.py — portable hardware probing for ML feasibility (CPU cores,
      RAM, GPU, CUDA toolkit version, disk I/O bandwidth)

    Repository

    • README.md and AGENTS.md updated with both new skills (alphabetical order)
    • All skills follow the Agent Skills open format (agentskills.io)
    • MIT licensed
    Downloads
  • v0.1.1 cecdecf6b0

    v0.1.1 Stable

    jasper released this 2026-05-22 16:13:15 -04:00 | 26 commits to main since this release

    v0.1.1 — 2026-05-22

    Fix

    • cli-builder: Aligned Phase 4 architecture diagram with the scripts/ convention used by every other skill in the repo. The "Completed Architecture" section now shows the CLI binary in scripts/ within the skill directory, following the Agent Skills open format. Added a deployment model comparison table (scripts/ inside skill vs global PATH) with default recommendation. Updated the Two-Layer Architecture intro to use a concrete directory tree instead of abstract ASCII art. (PR #20, raised by neopabo)
    Downloads
  • v0.1.0 14d0735491

    v0.1.0 — Initial Release Stable

    jasper released this 2026-05-21 23:54:58 -04:00 | 32 commits to main since this release

    agent-skills v0.1.0 — Initial Release

    18 skills for AI agents, organized into three categories.

    Design & Methodology

    • cli-builder — 10 patterns for building agent-friendly CLI tools. Template, test suite, Python client pattern, skillify workflow.
    • systematic-debugging — 4-phase root cause debugging protocol. Schema/environment divergence, exception siblings, Rule of Three.
    • software-architecture-analysis — Codebase to clean-room PRD. Interface extraction pattern for swappable provider abstractions.
    • data-architect — Virtual data architect: discover, assess, design, govern.
    • agent-skills — Meta-skill: the Agent Skills open format reference.

    API CLIs — Atlassian

    • jira-cli — Search (JQL), view, create, comment, transition issues.
    • confluence-cli — Spaces, pages with body extraction, CQL search, create.

    API CLIs — Media & Entertainment

    • tmdb-cli — Movie and TV discovery by genre, certification, rating, date.
    • jellyfin-cli — Media server: recent items, search, libraries, stats.
    • arr-cli — Radarr + Sonarr: movies and series management, calendars, wanted.
    • trakt — Media discovery: trending, anticipated, popular (read-only).
    • tempest-cli — Hyper-local weather from your Tempest station.

    API CLIs — Content & Publishing

    • ghost-cli — CMS: posts, pages, tags via Admin API (JWT auth).
    • transistor — Podcast hosting: shows, episodes, subscriber analytics.
    • peertube — Federated video: browse, search, channels (OAuth2).

    API CLIs — Self-Hosted Utilities

    • forgejo-cli — Self-hosted Git forge: repos, issues, PRs.
    • openlibrary-cli — Book metadata: search, ISBN lookup (no API key).

    74 files, ~8,100 lines across 18 skills. Every CLI built with the cli-builder patterns: --json, --dry-run, lazy auth, emit() dual-output, pre-parsed global flags, structured logging.

    MIT licensed.

    Downloads